The goal of this paper is to take a single 2D image of a scene and recover
the 3D structure in terms of a small set of factors: a layout representing the
enclosing surfaces as well as a set of objects represented in terms of shape
and pose. We propose a convolutional neural network-bas
该论文提出了一种名为 Shape-Net 的方法,通过将 2D 全景和 3D 信息提供给模型,引入 3D IoU 损失来解决遮挡问题,同时通过从同时利用图像和 3D 信息训练的模型中提取知识来解决实际情况下缺乏建筑图纸的问题。该模型是基于现有模型进行改良,实现了对房间布局的精确估算,同时能够有效处理具有遮挡的情况。